engagement-poll
Skill17 starsChanged 7 months agoMITView on GitHub
Design polls and audience questions for X, LinkedIn, and Instagram Stories — audience research disguised as engagement, with post templates and follow-up strategies.
In this repository40 other files it gives its agents.
- ab-test-analyzeSkill
- metrics-trackSkill
- performance-reportSkill
- caption-draftSkill
- cta-craftSkill
- hook-writeSkill
- post-createSkill
- thread-createSkill
- apology-draftSkill
- crisis-respondSkill
- impersonator-monitorSkill
- comment-replySkill
- dm-respondSkill
- influencer-outreachSkill
- mention-monitorSkill
- cadence-timingSkill
- content-calendarSkill
- presence-refreshSkill
- profile-auditSkill
- cross-post-adaptSkill
- draft-reviewSkill
- schedule-queueSkill
- thread-structureSkill
- blog-to-threadSkill
- newsletter-to-postsSkill
- podcast-to-clipsSkill
- competitor-content-auditSkill
- prospect-social-auditSkill
- social-profile-discoverSkill
- brand-voice-systemSkill
- content-pillarsSkill
- crm-social-bridgeSkill
- positioning-statementSkill
- news-responseSkill
- trending-briefingSkill
- trend-monitorSkill
- asset-formatSkill
- image-promptSkill
- meme-createSkill
- visual-planSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
Before a product launch (gauge interest, segment audience)
- Distinctive: line 56
Every poll serves both, not just one
- Distinctive: line 73
All options equally valid (no obviously "right" answer)
- Distinctive: line 112
Follow-up results post is planned
- Distinctive: line 118
Never sharing results (waste of audience participation)
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Engagement Poll
Design polls, questions, and interactive content that boosts engagement AND generates audience insight. A good poll does double duty: it feeds the algorithm AND feeds your understanding of the audience.
Purpose
Polls are the highest-RPM content type for engagement. They take the audience 2 seconds to interact with, tell the algorithm "people are engaging with this brand," and give you free market research. This skill designs polls that serve both purposes.
When to Use
- Weekly engagement-boost slot in the content calendar
- Audience research needed (validate ideas, measure preferences)
- Low-engagement period (poll resets algorithmic momentum)
- Before a product launch (gauge interest, segment audience)
Inputs Required
- Poll purpose (engagement boost, audience insight, or both)
- Target platform
- What you want to learn (the insight goal)
- Brand voice guide
Quick Reference
| Poll Type | Best Platform | Format | Example |
| Binary choice | X, LinkedIn, IG Stories | "A or B?" + context | "Which is harder: first 10 customers or first 100?" |
| Preference | IG Stories, X | "Which [X] do you prefer?" | "What format helps you most: threads, videos, or carousels?" |
| Agree-Disagree | LinkedIn, X | Statement + agree/disagree | "Founders should do CS for the first year. Agree?" |
| Open-ended question | LinkedIn, X | "Reply with your answer" | "What's one metric that changed your decisions?" |
| Ranking | IG Stories (slider), X | "Rate 1-10" | "How confident in your pricing? 1-10" |
Procedure
- Define dual purpose:
- Primary: engagement boost (algorithm)
- Secondary: audience insight (what do we learn?)
- Every poll serves both, not just one
- Choose platform and format:
- X: native poll (4 options, 1 day duration)
- LinkedIn: native poll (4 options, 1-2 weeks)
- IG Stories: poll/question/slider stickers
- TikTok: Q&A feature, comments-based
- Write the poll question:
- Genuinely interesting to audience (not just to you)
- No leading questions
- Specific (broad = generic answers)
- 1-2 sentences of context + the poll
- Write poll options:
- 2 options: simple, high response rate
- 3-4 options: nuanced, slightly lower response
- All options equally valid (no obviously "right" answer)
- Plan the follow-up:
- Results post: share results + your analysis (48 hours after poll closes)
- Tag or DM respondents with interesting takes
Output Format
# Poll: [Topic]
## Purpose
**Primary:** [Engagement boost / Algorithm reset]
**Secondary:** [What do you want to learn?]
## Platform: [X / LinkedIn / IG Stories / TikTok]
## Poll Content
**Question:** [Poll text]
**Options:**
1. [Option 1]
2. [Option 2]
3. [Option 3] (optional)
4. [Option 4] (optional)
**Duration:** [1 day / 3 days / 1 week]
**Supporting caption:** [Context]
## Follow-Up Plan
- **Results post:** [Date/time — 48h after poll closes]
- **Results angle:** [What insight emerged]
- **Engagement from results:** [Reply, tag interesting commenters]Done Criteria
The skill is complete when:
- Poll question is clear and specific
- Options are equally valid (no correct answer)
- Platform and format are matched
- Follow-up results post is planned
Pitfalls
- Thinly veiled marketing polls ("Would you buy our product: Yes or Definitely Yes?")
- Questions the audience doesn't care about
- Never sharing results (waste of audience participation)
- More than 2 poll-style posts per week (fatigue)
- Binary polls where both options are basically the same
Verification
Would you vote on this if you saw it in your feed? Is the question genuinely interesting or just filler? Will the results change anything about how the brand operates? Is the follow-up results post planned?
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

